cs.AI updates on arXiv.org 07月08日 13:54
Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种基于卷积神经网络的声音转换方法,通过调整音高、音节速率等参数,实现声音的灵活转换,并保持高可懂度和说话人相似度。

arXiv:2507.04817v1 Announce Type: cross Abstract: Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important element for effective identity conversion, but can also be used independently for voice transformation, achieving goals that were historically addressed by vocoder-based methods. In this work, we explore a convolutional neural network-based approach that aims to provide means for modifying fundamental frequency (F0), phoneme sequences, intensity, and speaker identity. Rather than relying on disentanglement techniques, our model is explicitly conditioned on these factors to generate mel spectrograms, which are then converted into waveforms using a universal neural vocoder. Accordingly, during inference, F0 contours, phoneme sequences, and speaker embeddings can be freely adjusted, allowing for intuitively controlled voice transformations. We evaluate our approach on speaker conversion and expressive speech tasks using both perceptual and objective metrics. The results suggest that the proposed method offers substantial flexibility, while maintaining high intelligibility and speaker similarity.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

声音转换 卷积神经网络 音高调整 说话人相似度
相关文章